mrtydi-v1.1-ar.yaml

---
corpus: mrtydi-v1.1-ar
corpus_path: collections/mr-tydi-corpus/mrtydi-v1.1-arabic/

index_path: indexes/lucene-index.mrtydi-v1.1-arabic/
collection_class: MrTyDiCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 1
index_options: -storePositions -storeDocvectors -storeRaw -language ar
index_stats:
  documents: 2106586
  documents (non-empty): 2106586
  total terms: 92529032

metrics:
  - metric: MRR@100
    command: bin/trec_eval
    params: -c -M 100 -m recip_rank
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: true
  - metric: R@100
    command: bin/trec_eval
    params: -c -m recall.100
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: true

topic_reader: TsvInt
topics:
  - name: "[Mr. TyDi (Arabic): train](https://github.com/castorini/mr.tydi)"
    id: train
    path: topics.mrtydi-v1.1-ar.train.txt.gz
    qrel: qrels.mrtydi-v1.1-ar.train.txt
  - name: "[Mr. TyDi (Arabic): dev](https://github.com/castorini/mr.tydi)"
    id: dev
    path: topics.mrtydi-v1.1-ar.dev.txt.gz
    qrel: qrels.mrtydi-v1.1-ar.dev.txt
  - name: "[Mr. TyDi (Arabic): test](https://github.com/castorini/mr.tydi)"
    id: test
    path: topics.mrtydi-v1.1-ar.test.txt.gz
    qrel: qrels.mrtydi-v1.1-ar.test.txt

models:
  - name: bm25
    display: BM25
    params: -bm25 -hits 100 -language ar
    results:
      MRR@100:
        - 0.3356
        - 0.3462
        - 0.3682
      R@100:
        - 0.7944
        - 0.7872
        - 0.7928